INDEX

Explanations

mathematical symbols or notations used in scientific equations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.68

uxxxx

-0.64

Personendaten

-0.61

 køb

-0.57

 تضيفلها

-0.56

 læng

-0.55

IndentedString

-0.52

 estimés

-0.52

habitude

-0.52

 Мексичка

-0.52

POSITIVE LOGITS

endpush

0.53

 Sinai

0.51

didSet

0.49

YG

0.45

endphp

0.44

jsonwebtoken

0.43

bcryptjs

0.43

 OMITBAD

0.42

 TestBed

0.42

󠁿

0.41

Activations Density 0.513%

mathematical symbols or notations used in scientific equations

No Comments

No Known Activations